Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    analytical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Сов
    -0.07
    ंतर
    -0.06
    eon
    -0.06
    ovo
    -0.06
    icol
    -0.06
     incontro
    -0.06
    ент
    -0.06
    ragon
    -0.06
     Elsa
    -0.06
    stead
    -0.06
    POSITIVE LOGITS
    (cv
    0.07
    (ph
    0.07
    .graph
    0.07
    ph
    0.07
    Router
    0.07
    ｀
    0.07
     değ
    0.06
     производства
    0.06
    shot
    0.06
    lot
    0.06
    Act Density 0.015%

    No Known Activations